基于小波包与遗传算法和支持向量机的液压泵故障诊断

Fault Diagnosis of Hydraulic Pump Based on Wavelet Packet and Genetic Algorithm as well as Support Vector Machine

针对液压泵振动信号信噪比低、非线性及小样本等特点,提出了一种基于小波包(Wavelet Packet,WP)分解、遗传算法(Genetic Algorithm,GA)和支持向量机(Support Vector Machine,SVM)的液压泵故障诊断模型,即WP-GA-SVM模型。首先对液压泵振动信号进行小波包消噪预处理,然后将消噪后的信号进行小波包分解与重构,提取频带能量作为支持向量机分类器的输入特征向量。采用遗传算法来实现支持向量机核函数参数g和惩罚因子C的自动快速最优选择。最后通过与概率神经网络方法对液压泵故障诊断的对比分析,验证了该模型的有效性和优越性。

According to the characteristics of the hydraulic pump vibration signal-the low signal、nonlinear and small sample, a model of hydraulic pump fault diagnosis based on wavelet packet, the genetic algorithm and support vector machine （ SVM ） was proposed. Firstly, the hydraulic pump vibration signal was de-noised and preprocessed by the wavelet packet;then the feature of band-energy was extracted by the wavelet packet decomposition and reconstructed as the input vector of the SVM classifier. Genetic algorithm was used to achieve automatic and optimal choose of the parameter g of radial basis kernel function and penalty parameter C. Finally, by contrast with the probabilistic neural network to the hydraulic pump fault diagno-sis, we verified the effectiveness and superiority of the proposed model.